© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172259
    Prev
    Next
    INDEX
    Explanations

    letter sound recognition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     குறை
    0.44
    microwave
    0.43
    摂
    0.43
     audiobook
    0.43
    cof
    0.42
     facilitators
    0.42
    рую
    0.42
    ουλ
    0.41
    用於
    0.40
    數學
    0.40
    POSITIVE LOGITS
    </h3>
    0.45
     ചേർ
    0.45
    豸
    0.44
     ángulos
    0.42
     leopard
    0.41
     legs
    0.41
     joints
    0.41
     vért
    0.40
    人不
    0.40
     famili
    0.38
    Activations Density 0.002%

    No Known Activations